metadata
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: MAE Model (model_idx_0614)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | MAE |
| Split | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 614 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9750 |
| Val Accuracy | 0.8685 |
| Test Accuracy | 0.8786 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
poppy, table, baby, raccoon, porcupine, sunflower, chimpanzee, squirrel, shark, pickup_truck, skunk, willow_tree, woman, house, wolf, apple, sweet_pepper, mountain, hamster, can, keyboard, forest, lobster, dolphin, camel, snake, beetle, cup, bridge, tank, trout, bottle, crab, whale, bear, kangaroo, rose, elephant, tractor, rabbit, cockroach, possum, dinosaur, spider, caterpillar, seal, leopard, bicycle, road, mushroom